spatial_intersect

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description needn't restate safety. However, it adds almost no behavioral context beyond that — it doesn't clarify coordinate system, behavior when no field value exists at the point, or whether multiple fieldIds are returned as a composite. With openWorldHint=true also set, the description does not explain what that implies for the agent. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single seven-word fragment is terse, but this is under-specification rather than concise efficiency. For a tool with three required parameters and no output schema, the description front-loads nothing of substance and leaves the agent without critical call details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must convey return shape, yet it only says 'values... at a point' with no mention of structure, ordering, or error behavior. For a 3-required-parameter spatial tool this is materially incomplete — an agent cannot predict the response or handle edge cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% (fieldIds has a description; lat and lng are bare numbers). The description fails to compensate: it says nothing about lat/lng format, units, or coordinate reference system, which are essential for a spatial point query. It only loosely reinforces that fieldIds means 'one or more fields', already implied by the schema. At 33% coverage the description was obligated to document the undocumented params and did not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource ('fields at a point') but omits a verb — it is a fragment, not a statement of action. 'Values of one or more fields at a point' implies a read/sample operation, but the agent must infer the verb. It does hint at distinction from siblings like spatial_get_field (which returns field definitions) via the 'at a point' spatial qualifier, but this is indirect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus the many siblings. Given related tools such as spatial_search_gazetteer, spatial_get_field, and spatial_list_fields, the description gives no context on selection criteria, exclusions, or prerequisites. An agent cannot tell when to pick this over spatial_get_field without opening other definitions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.